Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Use this agent when you need to manage project tasks using the llm-backlog CLI tool. This includes creating new tasks, editing tasks, ensuring tasks follow the proper format and guidelines, breaking down large tasks into atomic units, and maintaining the project's task management workflow.
Agent Claude Code
Your AI team. Describe what you're building, get a team of specialists that live in your repo.
Ratnam-Mishra/canvas-apps-plugin-codex
Agent Claude Code
Plans and designs a Canvas App. Discovers available controls, APIs, and data sources; calls describeapi for relevant connectors and getdatasourceschema for connected data sources; designs the aesthetic direction and screen plan; presents plan for user approval via a markdown approval prompt; calls describecontrol for…
Agent Claude Code
A project-memory curator for GraphMind, a system that stores connected notes and facts about a project.
Agent Claude Code
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
Agent Claude Code needs its repo
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
RoninForge/roninforge-tailwind-v4
Agent Claude Code
Reviews code changes for correct Tailwind CSS v4 usage. Catches v3 patterns, missing accessibility attributes, and inconsistent theming. Use after generating or modifying Tailwind code.
Agent Claude CodeCursor
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
Agent Claude CodeOpenCode
The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.
Agent Claude Code
Developer agent (Agent-Dev). Use it to implement features, write or modify production code, and fix bugs. When done, it automatically commits its work with the Agent-Dev label and the LoC count.
SufficientDaikon/sdd-vscode-agents
Agent Claude Code
Spec-Driven Development agent that takes a comprehensive specification and implements it faithfully, section by section. Follows the spec exactly, writes tests based on acceptance criteria, and verifies each section works before moving to the next.
Agent Claude Code
A domain-specialist agent for the GovOn AX platform, using trained models for public administration and law. It is intended to answer questions about administrative procedures, permits, complaints, legislation, and court decisions.
Agent Claude Code
Reviews API-facing changes for breaking edits and missing docs.
Agent Claude Code
An agent role for making the smallest needed code or documentation change. It follows existing project style and uses TDD, meaning tests are written before the implementation.
stepanenkoviktor0110-boop/ai-dev-methodology
Agent Claude Code
Validates task files against task template and task-creator rules. Reads sources of truth, checks structure, content quality, and consistency. Triggers: after task-creator generates files, on re-validation after fixes. Not for: security (security-auditor), spec coverage (completeness-validator).
aget-framework/template-advisor-aget
Agent Claude Code
Place subagent definition files here. Each .md file defines a specialized subagent that can be invoked via the Task tool or --agent flag.
xinshixu7170/independent-critic
Agent Claude Code
Independently reviews a proposal / change / conclusion in a fresh subagent context. It does not inherit the conversation transcript, but it does receive the parent-written delegation prompt and the session's CLAUDE.md hierarchy, so it must verify claims against primary sources. 🔴 Main session: invoke it yourself…
CCDevelopForFun/agent-controller
Agent Claude Code
SQL exploration specialist with time-awareness capabilities.
Agent Claude Code
Read-only architecture designer/reviewer: creates target designs, maps intended vs observed structure, gathers evidence, scores architecture, and writes plans without editing source.
Agent Claude Code
Taskboard Manager. Tracks stateful progress and manages the project ledger. Use for maintaining the "Source of Truth" for tasks.
alessio-locatelli/ceo-agent-workflow
Agent Claude Code
Hands‑on technical leader who translates product vision into scalable architecture, mentors engineers, and drives delivery excellence. Proactively steps in during sprint kickoff, when architectural decisions surface, or whenever blockers threaten timelines—to ensure the team stays aligned, code quality remains high…
danstrem2/clawdbot-skill-master-pack
Agent Claude Code
Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.
Agent Claude Code
Use this agent when you need to understand and list OpenShift CI components including workflows, chains, and refs in a hierarchical structure.
Agent Claude Code
Mobile-first responsive design expert. Use for layout reviews, mobile optimization, information density, touch accessibility, or creating responsive components.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: